Self-Supervised Linear Motion Deblurring

@article{Liu2020SelfSupervisedLM,
  title={Self-Supervised Linear Motion Deblurring},
  author={Peidong Liu and Joel Janai and Marc Pollefeys and Torsten Sattler and A. Geiger},
  journal={IEEE Robotics and Automation Letters},
  year={2020},
  volume={5},
  pages={2475-2482}
}
  • Peidong Liu, Joel Janai, +2 authors A. Geiger
  • Published 2020
  • Computer Science
  • IEEE Robotics and Automation Letters
  • Motion blurry images challenge many computer vision algorithms, e.g., feature detection, motion estimation, or object recognition. Deep convolutional neural networks are state-of-the-art for image deblurring. However, obtaining training data with corresponding sharp and blurry image pairs can be difficult. In this letter, we present a differentiable reblur model for self-supervised motion deblurring, which enables the network to learn from real-world blurry image sequences without relying on… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 45 REFERENCES
    Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
    • 472
    • Highly Influential
    • PDF
    High-quality motion deblurring from a single image
    • 1,035
    • Highly Influential
    • PDF
    Reblur2Deblur: Deblurring videos via self-supervised learning
    • 27
    • Highly Influential
    • PDF
    Deep Video Deblurring for Hand-Held Cameras
    • 148
    • PDF
    Non-uniform Deblurring for Shaken Images
    • 536
    • PDF
    DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
    • 379
    • Highly Influential
    • PDF
    Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks
    • 72
    • PDF
    Generalized video deblurring for dynamic scenes
    • 88
    • PDF
    Unsupervised Monocular Depth Estimation with Left-Right Consistency
    • 1,072
    • PDF
    Single Image Deblurring Using Motion Density Functions
    • 313
    • PDF